Closed yangcaoai closed 2 years ago
I found the reasons. Some images from SUNRGB-D have no objects. So there are no box labels.
@yangcaoai how do you resolve this error?
@yangcaoai how do you resolve this error?
@yxchng When encountering input data batch without labels, I skipped the loss computation in this way: https://github.com/yangcaoai/CoDA_NeurIPS2023/blob/main/criterion.py#L216
Hi, dear author, thanks for the excellent work!
When I try to train 3detr with 8 gpus. I found the training is hang on after some iterations. Then I found that the reason is that targets["num_boxes_replica"]=0. But I am curious that why it will become 0
Looking forward to your reply. Thanks.